import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from statistics import mean, median
from math import sqrt
from scipy.stats import mannwhitneyu
from typing import Tuple, List, Dict, Set, Iterable
import matplotlib.style as mpl_style
import os
import json

# path to csv results
AIRFOIL_PATH = "./results.csv"

def df_from_path(path: str) -> pd.DataFrame:
    return pd.read_csv(
        filepath_or_buffer=path,
        sep="?",
    )

AIRFOIL_RESULTS = df_from_path(AIRFOIL_PATH)
AIRFOIL_RESULTS.tail()

	directory	rund_id	test_no	generation	after_selection_depth_25percentile	after_selection_depth_50percentile	after_selection_depth_75percentile	after_selection_depth_algorithm	after_selection_depth_avg	after_selection_depth_avg_lev_distance_denoising	...	training_error	training_errors	training_mode	unique	unique_output_vector_rate	unique_output_vector_rate_int	unique_output_vector_rate_sel	unique_output_vector_rate_test	unique_rate	wass_norm_lev_div_sampled_vs_selected
1142	benchmark_runtime_daegp	5_3387	5	26	0.0	0.0	0.0	DAE_LSTM	0.078	0.048	...	0.011	None	convergence	65	0.106	0.076	0.05	0.106	0.130	0.15
1143	benchmark_runtime_daegp	5_3387	5	27	0.0	0.0	0.0	DAE_LSTM	0.160	0.086	...	0.014	None	convergence	405	0.726	0.404	0.066	0.726	0.810	0.146
1144	benchmark_runtime_daegp	5_3387	5	28	1.0	3.0	5.0	DAE_LSTM	3.500	0.408	...	0.014	None	convergence	263	0.488	0.260	0.43	0.488	0.526	0.094
1145	benchmark_runtime_daegp	5_3387	5	29	0.0	1.0	8.0	DAE_LSTM	3.864	0.580	...	0.015	None	convergence	42	0.082	0.046	0.29	0.082	0.084	0.116
1146	benchmark_runtime_daegp	5_3387	5	30	0.0	0.0	0.0	DAE_LSTM	0.102	0.054	...	0.02	None	convergence	63	0.104	0.050	0.06	0.104	0.126	0.071

5 rows × 787 columns

def split_df(df: pd.DataFrame, dir1: str, dir2: str) -> Tuple[pd.DataFrame, pd.DataFrame]:
    return df.query("directory == @dir1").copy(), df.query("directory == @dir2").copy()
    
pt_results, reg_results = split_df(AIRFOIL_RESULTS, "pt_dae_gp", "dae_gp")
gp_results, _ = split_df(AIRFOIL_RESULTS, "gp", "dae_gp")

print(
    pt_results.shape == reg_results.shape ==gp_results.shape,
    pt_results.shape,
    reg_results.shape,
    gp_results.shape

)

True (310, 787) (310, 787) (310, 787)

def filter_df_by_headers(df, headers):
    return df[df.columns.intersection(headers)]

def get_test_nums(df) -> Set[int]:
    return {x for x in df.test_no}

pt_test_nums = get_test_nums(pt_results)
reg_test_nums = get_test_nums(reg_results)
gp_test_nums = get_test_nums(reg_results)

def get_rund_ids(df) -> Set[int]:
    return {x for x in df.rund_id}

pt_rund_ids = get_rund_ids(pt_results)
reg_rund_ids = get_rund_ids(reg_results)
gp_rund_ids = get_rund_ids(gp_results)

PT_NRUNS = len(pt_rund_ids)
REG_NRUNS = len(reg_rund_ids)
GP_NRUNS = len(gp_rund_ids)

print(f"Pre-Trained Runs: {PT_NRUNS}\nRegular Runs: {REG_NRUNS}\nGP Runs: {GP_NRUNS}")

Pre-Trained Runs: 10
Regular Runs: 10
GP Runs: 10

D = {
    "hidden_layers": 2,
    "gen_max": 30,
    "n_runs": 10
}

def validate(D: Dict, df: pd.DataFrame, gp: bool=False):

    def check_hidden_layers(df: pd.DataFrame, value: str) -> bool:
        return all(df['hidden_layers'] == value)

    if not gp:
        print("Correct number of Hidden Layers: ", check_hidden_layers(df, D["hidden_layers"]))


    def check_generations_range(df: pd.DataFrame, minimum: int, maximum: int) -> bool:
        return all(df['generation'] >= minimum) and all(df['generation'] <= maximum)

    print("Correct number of Generations: ", check_generations_range(df, 0, D["gen_max"]))

    def get_ind_rund_ids(df):
        return len({x for x in df.rund_id})

    print("Minimum number of Runs reached: ", get_ind_rund_ids(df) >= D["n_runs"])


print("Regular Results:\n...")
validate(D, reg_results) 
print("\nPre-trained Results:\n...")
validate(D, pt_results)
print("\nGP Results:\n...")
validate(D, gp_results, gp=True)
print()

Regular Results:
...
Correct number of Hidden Layers:  True
Correct number of Generations:  True
Minimum number of Runs reached:  True

Pre-trained Results:
...
Correct number of Hidden Layers:  True
Correct number of Generations:  True
Minimum number of Runs reached:  True

GP Results:
...
Correct number of Generations:  True
Minimum number of Runs reached:  True

def get_vals(df, vals, gens):

    ret = []

    def filter_df_by_col_val(df, col, val):
        return df[df[col] == val]

    def get_rund_ids(df) -> Set[int]:
        return {x for x in df.rund_id}
    
    run_ids = get_rund_ids(df)

    for i, id in enumerate(run_ids):

        _df = filter_df_by_col_val(df, "rund_id", id)

        ret.append([])

        for gen in range(0,gens+1):

            __df = filter_df_by_col_val(_df, "generation", gen)

            ret[i].append(
                __df[vals].values[0]
            )
    return ret


reg_fits = get_vals(reg_results, "best_fitness", 30)
reg_fits_test = get_vals(reg_results, "best_fitness_test", 30)

pt_fits = get_vals(pt_results, "best_fitness", 30)
pt_fits_test = get_vals(pt_results, "best_fitness_test", 30)

gp_fits = get_vals(gp_results, "best_fitness", 30)
gp_fits_test = get_vals(gp_results, "best_fitness_test", 30)


def get_means(arr):

    ret = []

    for gen in range(0, 31):

        gen_fits=[]

        for run in range(0, len(arr)):

            gen_fits.append(arr[run][gen])
    
        ret.append(mean(gen_fits))

    return ret
        


reg_fits_mean = get_means(reg_fits)
reg_fits_test_mean = get_means(reg_fits_test)

pt_fits_mean = get_means(pt_fits)
pt_fits_test_mean = get_means(pt_fits_test)

gp_fits_mean = get_means(gp_fits)
gp_fits_test_mean = get_means(gp_fits_test)


def get_medians(arr):

    ret = []

    for gen in range(0, 31):

        gen_fits=[]

        for run in range(0, len(arr)):

            gen_fits.append(arr[run][gen])
    
        ret.append(median(gen_fits))

    return ret


reg_fits_med = get_medians(reg_fits)
reg_fits_test_med = get_medians(reg_fits_test)

pt_fits_med = get_medians(pt_fits)
pt_fits_test_med = get_medians(pt_fits_test)

gp_fits_med = get_medians(gp_fits)
gp_fits_test_med = get_medians(gp_fits_test)

DATAPATH = "/Users/rmn/masterThesis/master_thesis/data/airfoil_2hl_maxIndSize_fullRun_30gens_withGP"

def writeMWU(dir_name: str, file_name:str, sample1: Iterable, sample2: Iterable):
    if not os.path.exists(dir_name):
        os.makedirs(dir_name)

    statistic, pval = mannwhitneyu(x=sample1, y=sample2)

    S = {
        "statistic" : statistic,
        "p-value"   : pval
    }
    print(S)

    json.dump(
        S,
        open(os.path.join(dir_name, f"{file_name}.json"), "w", encoding="utf-8"),
    )

from json import load

MPL_CONFIG = load(
    open("/Users/rmn/masterThesis/eda-gp-2020/experiments/matplotlib_config.json", "r", encoding="utf-8")
)


mpl_style.use(MPL_CONFIG["mpl_style"])

# font sizes
SMALL=MPL_CONFIG["fonts"]["small"]
MID=MPL_CONFIG["fonts"]["mid"]
BIG=MPL_CONFIG["fonts"]["big"]

# color codes
C_REG=MPL_CONFIG["colors"]["dae-gp"]
C_PT=MPL_CONFIG["colors"]["pt_dae-gp"]
C_GP=MPL_CONFIG["colors"]["gp"]

# marker codes
M_TRAIN=MPL_CONFIG["marker"]["train"]
M_TEST=MPL_CONFIG["marker"]["test"]

TRAIN_LINESTYLE=MPL_CONFIG["train_line_style"]

DPI=MPL_CONFIG["dpi"]


IMG_PATH=f"{MPL_CONFIG['image_base_path']}/airfoil_2hl_maxIndSize_fullRun_30gens_withGP"

def create_dir(dir_name):
    if not os.path.exists(dir_name):
        os.makedirs(dir_name)

create_dir(IMG_PATH)
BASE_TITLE="Airfoil 2 Hidden Layers"

fig, (axl, axr) = plt.subplots(ncols=2, layout="constrained", sharex=True, sharey=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]



fig.suptitle(f"{BASE_TITLE} - Best Fitness by generation", fontsize=BIG)
fig.supxlabel("Generations", fontsize=MID)
fig.supylabel("RMSE", fontsize=MID)

axl.set_title(f"Mean")
axl.plot(gens, reg_fits_mean, color=C_REG, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="DAE-GP(Train)")
axl.plot(gens, reg_fits_test_mean, color=C_REG, marker=M_TEST, label="DAE-GP(Test)")
axl.plot(gens, pt_fits_mean, color=C_PT, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="Pre-Trained(Train)")
axl.plot(gens, pt_fits_test_mean, color=C_PT, marker=M_TEST, label="Pre-Trained(Test)")
axl.plot(gens, gp_fits_mean, color=C_GP, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="GP(Train)")
axl.plot(gens, gp_fits_test_mean, color=C_GP, marker=M_TEST, label="GP(Test)")
axl.grid()

axr.set_title("Median")
axr.plot(gens, reg_fits_med, color=C_REG, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="DAE-GP(Train)")
axr.plot(gens, reg_fits_test_med, color=C_REG, marker=M_TEST, label="DAE-GP(Test)")
axr.plot(gens, pt_fits_med, color=C_PT, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="Pre-Trained(Train)")
axr.plot(gens, pt_fits_test_med, color=C_PT, marker=M_TEST, label="Pre-Trained(Test)")
axr.plot(gens, gp_fits_med, color=C_GP, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="GP(Train)")
axr.plot(gens, gp_fits_test_med, color=C_GP, marker=M_TEST, label="GP(Test)")
axr.grid()

axr.legend()


fig.savefig(f"{IMG_PATH}/mean_median_fitness_byGens.png")
writeMWU(DATAPATH, "MWU-BestFitnessByGen", pt_fits[0], reg_fits[0])

{'statistic': 84.0, 'p-value': 5.173868582401981e-09}

fig, axr = plt.subplots(ncols=1, layout="constrained", sharex=True, sharey=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]



fig.suptitle(f"{BASE_TITLE} - Median Best Fitness by generation", fontsize=BIG)
fig.supxlabel("Generations", fontsize=MID)
fig.supylabel("RMSE", fontsize=MID)


axr.plot(gens, reg_fits_med, color=C_REG, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="DAE-GP(Train)")
axr.plot(gens, reg_fits_test_med, color=C_REG, marker=M_TEST, label="DAE-GP(Test)")
axr.plot(gens, pt_fits_med, color=C_PT, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="Pre-Trained(Train)")
axr.plot(gens, pt_fits_test_med, color=C_PT, marker=M_TEST, label="Pre-Trained(Test)")
axr.plot(gens, gp_fits_med, color=C_GP, marker=M_TRAIN, linestyle=TRAIN_LINESTYLE, label="GP(Train)")
axr.plot(gens, gp_fits_test_med, color=C_GP, marker=M_TEST, label="GP(Test)")
axr.grid()

axr.legend(fontsize=MID)


fig.savefig(f"{IMG_PATH}/median_fitness_byGens.png")

def last_fits(arr):
    ret = []
    for run in arr:
        ret.append(run[-1])
    return ret

fig, ax = plt.subplots(layout="constrained", sharex=True, sharey=True, dpi=DPI)
fig.set_size_inches(14,12)

LABELS = ["DAE-GP(Train)", "DAE-GP(Test)", "Pre-Trained(Train)", "Pre-Trained(Test)", "GP(train)", "GP(test)"]
X = [
    last_fits(reg_fits),
    last_fits(reg_fits_test),
    last_fits(pt_fits),
    last_fits(pt_fits_test),
    last_fits(gp_fits),
    last_fits(gp_fits_test)

]

std_dev = np.std(X, 1)
means = np.mean(X,1)

fig.suptitle(f"{BASE_TITLE} - Best Fitness after 30 gens", fontsize=BIG)
fig.supylabel("RMSE", fontsize=MID)

bp_dict = ax.boxplot(
    x=X,
    labels=LABELS,
    #patch_artist=True,  # fill with color
    #notch=True,  # notch shape
)

for i, line in enumerate(bp_dict['medians']):
    x, y = line.get_xydata()[1]
    text = ' mean={:.2f}\n std_dev={:.2f}'.format(means[i], std_dev[i])
    ax.annotate(text, xy=(x, y))

ax.grid()
fig.savefig(f"{IMG_PATH}/final_fit_boxplot.png")

# epochs trained


reg_epochs = np.array(
    list(map(lambda x: [int(i) if i != "None" else 0 for i in x], get_vals(reg_results, "epochs_trained", 30)))
)
pt_epochs = np.array(
    list(map(lambda x: [int(i) if i != "None" else 0 for i in x], get_vals(pt_results, "epochs_trained", 30)))
)

gens = np.arange(1,31)

reg_epochs_mean = reg_epochs.mean(axis=0)
pt_epochs_mean = pt_epochs.mean(axis=0)

fig,ax = plt.subplots()
fig.set_size_inches(14,12)

fig.suptitle(f"{BASE_TITLE} - Training epochs", fontsize=BIG)

#ax.set_ylim(bottom=0, top=1)
ax.set_xlim(left=1, right=30)
    
ax.plot(gens, reg_epochs_mean[1:], color=C_REG, label="DAE-GP")
ax.plot(gens, pt_epochs_mean[1:], color=C_PT, label="Pre-Trained")

ax.set_ylabel("Epochs trained")
ax.set_xlabel("Generations")


ax.grid()
ax.legend()

fig.savefig(f"{IMG_PATH}/training_epochs.png")

# number of evals per generation


reg_nevals = get_vals(reg_results, "fitness_nevals", 30)
pt_nevals = get_vals(pt_results, "fitness_nevals", 30)
gp_nevals = get_vals(gp_results, "fitness_nevals", 30)


reg_nevals_mean = get_means(reg_nevals)
pt_nevals_mean = get_means(pt_nevals)
gp_nevals_mean = get_means(gp_nevals)


fig, ax = plt.subplots(layout="constrained", sharex=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]


fig.suptitle(f"{BASE_TITLE} - Mean Number of Fitness Evaluations", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)

ax.set_ylabel("Number of Fitness Evaluations")
ax.plot(gens, reg_nevals_mean, color=C_REG, label="DAE-GP")
ax.plot(gens, pt_nevals_mean, color=C_PT, label="Pre-Trained")
ax.plot(gens, gp_nevals_mean, color=C_GP, label="GP")

ax.grid()

ax.legend()


fig.savefig(f"{IMG_PATH}/mean_nevals_byGens.png")

df = pd.to_numeric(pt_results["hidden_dim"], errors='coerce').dropna()

print(
    df.mean()
)

136.2

# TODO: Change reg results to DAE_LSTM_fhn_Runtime_tingle

# plot total runtime

reg_time = get_vals(reg_results, "time_used", 30)
pt_time = get_vals(pt_results, "time_used", 30)
gp_time = get_vals(gp_results, "time_used", 30)


reg_time_mean = get_means(reg_time)
pt_time_mean = get_means(pt_time)
gp_time_mean = get_means(gp_time)



fig, (axl, axr) = plt.subplots(ncols=2, layout="constrained", sharex=True, sharey=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]

# axl.set_ylim(bottom=0, top=1)
axl.set_xlim(left=0, right=30)


fig.suptitle(f"{BASE_TITLE} - Mean Runtime", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)

fig.supylabel("Time [seconds]")

axl.set_title("Including Pre-Training Time")
axl.plot(gens, reg_time_mean, color=C_REG, label="DAE-GP")
axl.plot(gens, pt_time_mean, color=C_PT, label="Pre-Trained")
axl.plot(gens, gp_time_mean, color=C_GP, label="GP")

axl.grid()
axl.legend()

def subtract_and_remove(arr):
    new_arr = []
    for sub_arr in arr:
        first_val = sub_arr[0]
        new_sub_arr = [val - first_val for val in sub_arr[1:]]
        new_arr.append(new_sub_arr)
    return new_arr


reg_time_adj = subtract_and_remove(reg_time)     # [ arr[1:] for arr in reg_time ]
pt_time_adj = subtract_and_remove(pt_time)
gp_time_adj = subtract_and_remove(gp_time)       # [ arr[1:] for arr in gp_time ]


reg_time_adj_mean = np.mean(reg_time_adj, axis=0)
pt_time_adj_mean = np.mean(pt_time_adj, axis=0)
gp_time_adj_mean = np.mean(gp_time_adj, axis=0)


gens = [x for x in range(1, 31)]

axr.set_title("Excluding Pre-Training Time")
axr.plot(gens, reg_time_adj_mean, color=C_REG, label="DAE-GP")
axr.plot(gens, pt_time_adj_mean, color=C_PT, label="Pre-Trained")
axr.plot(gens, gp_time_adj_mean, color=C_GP, label="GP")

axr.grid()
axr.legend()


fig.savefig(f"{IMG_PATH}/runtime.png")

#  unique rate and lev diversity per generation

reg_levdiv = get_vals(reg_results, "norm_lev_div", 30)
pt_levdiv = get_vals(pt_results, "norm_lev_div", 30)
gp_levdiv = get_vals(gp_results, "norm_lev_div", 30)


reg_levdiv_mean = get_means(reg_levdiv)
pt_levdiv_mean = get_means(pt_levdiv)
gp_levdiv_mean = get_means(gp_levdiv)


reg_ur = get_vals(reg_results, "unique_rate", 30)
pt_ur = get_vals(pt_results, "unique_rate", 30)
gp_ur = get_vals(gp_results, "unique_rate", 30)

reg_ur_mean = get_means(reg_ur)
pt_ur_mean = get_means(pt_ur)
gp_ur_mean = get_means(gp_ur)



fig, (axl, axr) = plt.subplots(ncols=2, layout="constrained", sharex=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]

axl.set_ylim(bottom=0, top=1)
axl.set_xlim(left=0, right=30)


fig.suptitle(f"{BASE_TITLE} - Mean Population Diversity by generation", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)

axr.set_ylabel("Normalized Levenshtein Edit Distance")
axr.plot(gens, reg_levdiv_mean, color=C_REG, label="DAE-GP")
axr.plot(gens, pt_levdiv_mean, color=C_PT, label="Pre-Trained")
axr.plot(gens, gp_levdiv_mean, color=C_GP, label="GP")


axl.set_ylabel("Unique Rate")
axl.plot(gens, reg_ur_mean, color=C_REG, label="DAE-GP")
axl.plot(gens, pt_ur_mean, color=C_PT, label="Pre-Trained")
axl.plot(gens, gp_ur_mean, color=C_GP, label="GP")


axl.grid()
axr.grid()

axr.legend()


fig.savefig(f"{IMG_PATH}/mean_popDiversity_byGens.png")

# plot sample time

# plot mean size


reg_avgsize = get_vals(reg_results, "avg_size", 30)
pt_avgsize = get_vals(pt_results, "avg_size", 30)
gp_avgsize = get_vals(gp_results, "avg_size", 30)

reg_bestsize = get_vals(reg_results, "size_best_fitness", 30)
pt_bestsize = get_vals(pt_results, "size_best_fitness", 30)
gp_bestsize = get_vals(gp_results, "size_best_fitness", 30)

reg_avgsize_mean = get_means(reg_avgsize)
pt_avgsize_mean = get_means(pt_avgsize)
gp_avgsize_mean = get_means(gp_avgsize)

reg_bestsize_mean = get_means(reg_bestsize)
pt_bestsize_mean = get_means(pt_bestsize)
gp_bestsize_mean = get_means(gp_bestsize)





fig, (axl) = plt.subplots(layout="constrained", sharex=True, sharey=True, dpi=DPI)
fig.set_size_inches(10,8)
gens = [x for x in range(0, 31)]

# ax.set_ylim(bottom=0)
# ax.set_xlim(left=0)


fig.suptitle(f"{BASE_TITLE} -Mean Solution Size by generation", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)

axl.set_ylabel("Mean Tree Size")
axl.plot(gens, reg_bestsize_mean, color=C_REG, label="DAE-GP (Best Solution)")
#axl.plot(gens, reg_avgsize_mean, color=C_REG,linestyle=TRAIN_LINESTYLE, label="DAE-GP (Population average)")

axl.plot(gens, pt_bestsize_mean, color=C_PT, label="Pre-Trained (Best Solution)")
#axl.plot(gens, pt_avgsize_mean, color=C_PT, linestyle=TRAIN_LINESTYLE, label="Pre-Trained (Population average)")

axl.plot(gens, gp_bestsize_mean, color=C_GP, label="GP (Best Solution)")
#axl.plot(gens, gp_avgsize_mean, color=C_GP, linestyle=TRAIN_LINESTYLE, label="GP (Population average)")



axl.grid()

axl.legend()


fig.savefig(f"{IMG_PATH}/mean_Size_byGens.png")

# plot median best size


reg_avgsize = get_vals(reg_results, "avg_size", 30)
pt_avgsize = get_vals(pt_results, "avg_size", 30)
gp_avgsize = get_vals(gp_results, "avg_size", 30)

reg_bestsize = get_vals(reg_results, "size_best_fitness", 30)
pt_bestsize = get_vals(pt_results, "size_best_fitness", 30)
gp_bestsize = get_vals(gp_results, "size_best_fitness", 30)

reg_avgsize_mean = get_medians(reg_avgsize)
pt_avgsize_mean = get_medians(pt_avgsize)
gp_avgsize_mean = get_medians(gp_avgsize)

reg_bestsize_mean = get_means(reg_bestsize)
pt_bestsize_mean = get_means(pt_bestsize)
gp_bestsize_mean = get_means(gp_bestsize)





fig, (axl) = plt.subplots(layout="constrained", sharex=True, sharey=True, dpi=DPI)
fig.set_size_inches(10,8)
gens = [x for x in range(0, 31)]

# ax.set_ylim(bottom=0)
# ax.set_xlim(left=0)


fig.suptitle(f"{BASE_TITLE} -Median Size best Solution", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)

axl.set_ylabel("Tree Size", fontsize=MID)
axl.plot(gens, reg_bestsize_mean, color=C_REG, label="DAE-GP")
#axl.plot(gens, reg_avgsize_mean, color=C_REG,linestyle=TRAIN_LINESTYLE, label="DAE-GP (Population average)")

axl.plot(gens, pt_bestsize_mean, color=C_PT, label="Pre-Trained")
#axl.plot(gens, pt_avgsize_mean, color=C_PT, linestyle=TRAIN_LINESTYLE, label="Pre-Trained (Population average)")

axl.plot(gens, gp_bestsize_mean, color=C_GP, label="GP")
#axl.plot(gens, gp_avgsize_mean, color=C_GP, linestyle=TRAIN_LINESTYLE, label="GP (Population average)")



axl.grid()

axl.legend(fontsize=MID)


fig.savefig(f"{IMG_PATH}/median_best_Size_byGens.png")

# median lev diversity 
reg_levdiv = get_vals(reg_results, "norm_lev_div", 30)
pt_levdiv = get_vals(pt_results, "norm_lev_div", 30)
gp_levdiv = get_vals(gp_results, "norm_lev_div", 30)

reg_levdiv_median = get_medians(reg_levdiv)
pt_levdiv_median = get_medians(pt_levdiv)
gp_levdiv_median = get_medians(gp_levdiv)




fig, (axr) = plt.subplots(ncols=1, layout="constrained", sharex=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]

axl.set_ylim(bottom=0, top=1)
axl.set_xlim(left=0, right=30)


fig.suptitle(f"{BASE_TITLE} - Median Population Diversity by generation", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)
axr.set_ylabel("Normalized Levenshtein Distance",  fontsize=MID)

axr.plot(gens, reg_levdiv_median, color=C_REG, label="DAE-GP")
axr.plot(gens, pt_levdiv_median, color=C_PT, label="Pre-Trained")
axr.plot(gens, gp_levdiv_median, color=C_GP, label="GP")


axr.grid()

axr.legend(fontsize=MID)


fig.savefig(f"{IMG_PATH}/median_popDiversity_byGens_levOnly_withGP.png")

# median lev diversity 
reg_levdiv = get_vals(reg_results, "norm_lev_div", 30)
pt_levdiv = get_vals(pt_results, "norm_lev_div", 30)
gp_levdiv = get_vals(gp_results, "norm_lev_div", 30)

reg_levdiv_median = get_medians(reg_levdiv)
pt_levdiv_median = get_medians(pt_levdiv)
gp_levdiv_median = get_medians(gp_levdiv)




fig, (axr) = plt.subplots(ncols=1, layout="constrained", sharex=True, dpi=DPI)
fig.set_size_inches(14,12)
gens = [x for x in range(0, 31)]

axl.set_ylim(bottom=0, top=1)
axl.set_xlim(left=0, right=30)


fig.suptitle(f"{BASE_TITLE} - Median Population Diversity by generation", fontsize=BIG)

fig.supxlabel("Generations", fontsize=MID)
axr.set_ylabel("Normalized Levenshtein Distance",  fontsize=MID)

axr.plot(gens, reg_levdiv_median, color=C_REG, label="DAE-GP")
axr.plot(gens, pt_levdiv_median, color=C_PT, label="Pre-Trained")


axr.grid()

axr.legend(fontsize=MID)


fig.savefig(f"{IMG_PATH}/median_popDiversity_byGens_levOnly.png")

import datetime

def print_current_date_and_time():
  now = datetime.datetime.now()
  print(f'Notebook last executed at: {now.strftime("%Y-%m-%d %H:%M:%S")}')

print_current_date_and_time()

Notebook last executed at: 2023-01-23 09:41:20